{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH","short_pith_number":"pith:SIWXNJ7E","schema_version":"1.0","canonical_sha256":"922d76a7e44f2df0c3644fa8966d6b29cb646fa7fe45ff62294626dcfcbd8a73","source":{"kind":"arxiv","id":"1806.04185","version":1},"attestation_state":"computed","paper":{"title":"A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ani Nenkova, Benjamin Nye, Byron C. Wallace, Iain J. Marshall, Junyi Jessy Li, Roma Patel, Yinfei Yang","submitted_at":"2018-06-11T18:52:01Z","abstract_excerpt":"We present a corpus of 5,000 richly annotated abstracts of medical articles describing clinical randomized controlled trials. Annotations include demarcations of text spans that describe the Patient population enrolled, the Interventions studied and to what they were Compared, and the Outcomes measured (the `PICO' elements). These spans are further annotated at a more granular level, e.g., individual interventions within them are marked and mapped onto a structured medical vocabulary. We acquired annotations from a diverse set of workers with varying levels of expertise and cost. We describe o"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1806.04185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-11T18:52:01Z","cross_cats_sorted":[],"title_canon_sha256":"bd89351b3ad6af6729a951067daf214a007c1dc5cbdc6f355fcd1a0a933483c3","abstract_canon_sha256":"53cf3496671b738ff8c48da24c395b10b11333ceb2bfe7060cc5f362a89671df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:36.362570Z","signature_b64":"a0ScX8B10VEEF8tf/Ij2BykpmIlGf+YtlXOieFf7/obDxkcGLTmbzNO9/JuSZQFYWDvT2YAMBermHHDudpB0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"922d76a7e44f2df0c3644fa8966d6b29cb646fa7fe45ff62294626dcfcbd8a73","last_reissued_at":"2026-05-18T00:13:36.361852Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:36.361852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ani Nenkova, Benjamin Nye, Byron C. Wallace, Iain J. Marshall, Junyi Jessy Li, Roma Patel, Yinfei Yang","submitted_at":"2018-06-11T18:52:01Z","abstract_excerpt":"We present a corpus of 5,000 richly annotated abstracts of medical articles describing clinical randomized controlled trials. Annotations include demarcations of text spans that describe the Patient population enrolled, the Interventions studied and to what they were Compared, and the Outcomes measured (the `PICO' elements). These spans are further annotated at a more granular level, e.g., individual interventions within them are marked and mapped onto a structured medical vocabulary. We acquired annotations from a diverse set of workers with varying levels of expertise and cost. We describe o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04185","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1806.04185","created_at":"2026-05-18T00:13:36.361948+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.04185v1","created_at":"2026-05-18T00:13:36.361948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04185","created_at":"2026-05-18T00:13:36.361948+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIWXNJ7EJ4W7","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIWXNJ7EJ4W7BQ3E","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIWXNJ7E","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH","json":"https://pith.science/pith/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH.json","graph_json":"https://pith.science/api/pith-number/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH/graph.json","events_json":"https://pith.science/api/pith-number/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH/events.json","paper":"https://pith.science/paper/SIWXNJ7E"},"agent_actions":{"view_html":"https://pith.science/pith/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH","download_json":"https://pith.science/pith/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH.json","view_paper":"https://pith.science/paper/SIWXNJ7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.04185&json=true","fetch_graph":"https://pith.science/api/pith-number/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH/graph.json","fetch_events":"https://pith.science/api/pith-number/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH/action/storage_attestation","attest_author":"https://pith.science/pith/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH/action/author_attestation","sign_citation":"https://pith.science/pith/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH/action/citation_signature","submit_replication":"https://pith.science/pith/SIWXNJ7EJ4W7BQ3EJ6UJM3LLFH/action/replication_record"}},"created_at":"2026-05-18T00:13:36.361948+00:00","updated_at":"2026-05-18T00:13:36.361948+00:00"}